Tunable Q-factor Wavelet Transform Research Articles

An automated method for sleep staging from EEG signals using normal inverse Gaussian parameters and adaptive boosting

Sleep stage screening based on visual inspection is burdensome, time-consuming, subjective, and error-prone owing to the large bulk of data which have to be screened. Consequently, automatic sleep scoring is essential for both sleep research and sleep disorder diagnosis. In this work, we present the application of newly proposed tunable-Q factor wavelet transform (TQWT) to devise a single channel EEG based computerized sleep staging algorithm. First, we decompose the sleep-EEG signal segments into TQWT sub-bands. Then we perform normal inverse Gaussian (NIG) pdf modeling of TQWT sub-bands wherein NIG parameters are used as features. The effects of various TQWT parameters are also studied. The suitability of NIG parameters in the TQWT domain is inspected. In this study, we employ adaptive boosting (AdaBoost) for sleep stage classification. To assess the performance of the classification model and to determine the optimal choices of AdaBoost parameters, 10 fold cross-validation is performed. The performance of the proposed scheme is promising in terms of sensitivity, specificity, accuracy, and Cohen's Kappa co-efficient. Comparative analysis of performance suggests that the algorithmic performance of the proposed scheme, as opposed to that of the state-of-the-art ones is better. Further, the proposed algorithm also gives superior S1 and REM stage detection accuracy. The computerized sleep scoring scheme propounded herein can expedite sleep disorder diagnosis, contribute to the device implementation of a sleep monitoring system, and benefit sleep research.

A decision support system for automatic sleep staging from EEG signals using tunable Q-factor wavelet transform and spectral features

BackgroundAutomatic sleep scoring is essential owing to the fact that conventionally a large volume of data have to be analyzed visually by the physicians which is onerous, time-consuming and error-prone. Therefore, there is a dire need of an automated sleep staging scheme. New methodIn this work, we decompose sleep-EEG signal segments using tunable-Q factor wavelet transform (TQWT). Various spectral features are then computed from TQWT sub-bands. The performance of spectral features in the TQWT domain has been determined by intuitive and graphical analyses, statistical validation, and Fisher criteria. Random forest is used to perform classification. Optimal choices and the effects of TQWT and random forest parameters have been determined and expounded. ResultsExperimental outcomes manifest the efficacy of our feature generation scheme in terms of p-values of ANOVA analysis and Fisher criteria. The proposed scheme yields 90.38%, 91.50%, 92.11%, 94.80%, 97.50% for 6-stage to 2-stage classification of sleep states on the benchmark Sleep-EDF data-set. In addition, its performance on DREAMS Subjects Data-set is also promising. Comparison with existing methodsThe performance of the proposed method is significantly better than the existing ones in terms of accuracy and Cohen's kappa coefficient. Additionally, the proposed scheme gives high detection accuracy for sleep stages non-REM 1 and REM. ConclusionsSpectral features in the TQWT domain can discriminate sleep-EEG signals corresponding to various sleep states efficaciously. The proposed scheme will alleviate the burden of the physicians, speed-up sleep disorder diagnosis, and expedite sleep research.

Computer-aided obstructive sleep apnea detection using normal inverse Gaussian parameters and adaptive boosting

Abstract Automatic sleep apnea detection using single lead ECG is a precondition for the implementation of a sleep apnea monitoring device. Computerized sleep apnea screening is also essential for expediting sleep apnea research and alleviating the onus of physicians of analyzing a large volume of data by visual inspection. However, most of the state-of-the-art works on automated sleep apnea identification are either based on multiple leads and multiple physiological signals or yield poor performance. In this article, normal inverse Gaussian (NIG) pdf modeling in the recently proposed tunable-Q factor wavelet transform (TQWT) domain is introduced for computer-assisted sleep apnea diagnosis from single-lead ECG signals. First, ECG signal segments are decomposed into sub-bands using TQWT. Afterwards, the corresponding NIG parameters are computed from each of the sub-bands. These parameters are used as features in the proposed apnea detection algorithm. Adaptive boosting (AdaBoost), an eminent ensemble learning based classification scheme is employed to perform classification. The suitability of TQWT is analyzed. The effectiveness of the selected features is validated by intuitive, statistical, and graphical analyses. The performance of the proposed feature extraction scheme is evaluated for various choices of classifiers. Optimal choices of TQWT and AdaBoost parameters are also determined. The performance of the proposed method, as compared to the state-of-the-art algorithms, is comparable or superior in terms of various performance metrics.

Improved Ensemble Superwavelet Transform for Vibration-Based Machinery Fault Diagnosis

In the previous work of authors, the authors have presented an automatic fault feature extraction method, called ensemble superwavelet transform (ESW), based on the combination of tunable Q-factor wavelet transform (TQWT) and Hilbert transform. However, the nonstationary fault feature ratio which defined to guide the optimal wavelet basis selection does not take the interferences of high-frequency components into consideration. In addition, the original ESW utilizes one optimal subband to reconstruct the signal, which may result in the leakage of useful fault features. The present paper improves the ESW to address these problems. Specifically, the authors modify the definition of fault feature ratio by eliminating the high-frequency components when calculating total amplitudes of Hilbert envelope spectrum. Moreover, for the purpose of preserving more useful fault features and recovering the signal more accurately, a novel approach to reconstruct the processed result by incorporating two optimal subbands is proposed in this paper. The comprehensive comparisons by processing two simulation signals are provided to verify the effectiveness and utility of the improved ESW. Moreover, the improved ESW is applied to a range of engineering applications, and the obtained results demonstrate that the improved ESW can act as an effective technique in extracting weak fault features.

Tunable Q-factor Wavelet Transform for Extraction of Weak Bursts in the Vibration Signal of an Angular Contact Bearing

In this work feature extraction method making use of tunable Q-factor wavelet transform (TQWT) is applied for the ease of detection of bearing defect. Acquired vibration signal is decomposed into various sub-bands using TQWT. Then the signal is reconstructed from the band comprising highest energy. Finally, envelope demodulation of reconstructed signal is carried out. Defect frequency is spotted from the envelope spectrum for identification of defective component in the bearing.

Meet Spinky: An Open-Source Spindle and K-Complex Detection Toolbox Validated on the Open-Access Montreal Archive of Sleep Studies (MASS).

Sleep spindles and K-complexes are among the most prominent micro-events observed in electroencephalographic (EEG) recordings during sleep. These EEG microstructures are thought to be hallmarks of sleep-related cognitive processes. Although tedious and time-consuming, their identification and quantification is important for sleep studies in both healthy subjects and patients with sleep disorders. Therefore, procedures for automatic detection of spindles and K-complexes could provide valuable assistance to researchers and clinicians in the field. Recently, we proposed a framework for joint spindle and K-complex detection (Lajnef et al., 2015a) based on a Tunable Q-factor Wavelet Transform (TQWT; Selesnick, 2011a) and morphological component analysis (MCA). Using a wide range of performance metrics, the present article provides critical validation and benchmarking of the proposed approach by applying it to open-access EEG data from the Montreal Archive of Sleep Studies (MASS; O’Reilly et al., 2014). Importantly, the obtained scores were compared to alternative methods that were previously tested on the same database. With respect to spindle detection, our method achieved higher performance than most of the alternative methods. This was corroborated with statistic tests that took into account both sensitivity and precision (i.e., Matthew’s coefficient of correlation (MCC), F1, Cohen κ). Our proposed method has been made available to the community via an open-source tool named Spinky (for spindle and K-complex detection). Thanks to a GUI implementation and access to Matlab and Python resources, Spinky is expected to contribute to an open-science approach that will enhance replicability and reliable comparisons of classifier performances for the detection of sleep EEG microstructure in both healthy and patient populations.

Intelligent bearing fault signature extraction via iterative oscillatory behavior based signal decomposition (IOBSD)

A typical vibration signal from a defective bearing is composed of fault-induced transients (i.e., fault signature), resonance, multiple vibration interferences and background noise. Extracting the fault-induced transients from such signals is the primary goal for bearing fault diagnosis. This paper proposes an intelligent oscillatory behavior based signal decomposition (OBSD) method for this purpose. The OBSD technique exploits both the signal separation capability of morphological component analysis (MCA) and the basis creation potential of tunable Q-factor wavelet transform (TQWT). To generate proper bases for each individual signal component, the Q-factor determination and tuning strategies for the TQWT are developed in this study. In the presence of multiple interferences, one-time OBSD may not be sufficient to extract fault feature successfully. As such, an iterative OBSD (IOBSD) procedure is proposed. With the proposed method, a vibration signal can be decomposed into three signal components, i.e., low-oscillation component (fault signature presenting non-oscillation), high-oscillation component (interferences manifesting sustained oscillation) and residual (noise), according to their oscillatory behaviors. Bearing faults can then be reliably detected. The main features of the proposed method include: (1) it can remove in-band interference and noise that cannot be removed by the widely used frequency-based approaches, as it is frequency-independent in nature, (2) it can extract fault signatures from heavily interference-obscured signals without filtering the signals, and (3) it does not require the prior information of the signals. With these features, the IOBSD method can substantially reduce human involvement and facilitate its implementation in a fault detection expert system, particularly in an environment with various interferences. The IOBSD method has been favorably compared with one of the popular filtering techniques, i.e., SK method. The effectiveness of the proposed method has also been tested by simulation and experiments.

Sleep spindle and K-complex detection using tunable Q-factor wavelet transform and morphological component analysis.

A novel framework for joint detection of sleep spindles and K-complex events, two hallmarks of sleep stage S2, is proposed. Sleep electroencephalography (EEG) signals are split into oscillatory (spindles) and transient (K-complex) components. This decomposition is conveniently achieved by applying morphological component analysis (MCA) to a sparse representation of EEG segments obtained by the recently introduced discrete tunable Q-factor wavelet transform (TQWT). Tuning the Q-factor provides a convenient and elegant tool to naturally decompose the signal into an oscillatory and a transient component. The actual detection step relies on thresholding (i) the transient component to reveal K-complexes and (ii) the time-frequency representation of the oscillatory component to identify sleep spindles. Optimal thresholds are derived from ROC-like curves (sensitivity vs. FDR) on training sets and the performance of the method is assessed on test data sets. We assessed the performance of our method using full-night sleep EEG data we collected from 14 participants. In comparison to visual scoring (Expert 1), the proposed method detected spindles with a sensitivity of 83.18% and false discovery rate (FDR) of 39%, while K-complexes were detected with a sensitivity of 81.57% and an FDR of 29.54%. Similar performances were obtained when using a second expert as benchmark. In addition, when the TQWT and MCA steps were excluded from the pipeline the detection sensitivities dropped down to 70% for spindles and to 76.97% for K-complexes, while the FDR rose up to 43.62 and 49.09%, respectively. Finally, we also evaluated the performance of the proposed method on a set of publicly available sleep EEG recordings. Overall, the results we obtained suggest that the TQWT-MCA method may be a valuable alternative to existing spindle and K-complex detection methods. Paths for improvements and further validations with large-scale standard open-access benchmarking data sets are discussed.

Automatic fault feature extraction of mechanical anomaly on induction motor bearing using ensemble super-wavelet transform

Mechanical anomaly is a major failure type of induction motor. It is of great value to detect the resulting fault feature automatically. In this paper, an ensemble super-wavelet transform (ESW) is proposed for investigating vibration features of motor bearing faults. The ESW is put forward based on the combination of tunable Q-factor wavelet transform (TQWT) and Hilbert transform such that fault feature adaptability is enabled. Within ESW, a parametric optimization is performed on the measured signal to obtain a quality TQWT basis that best demonstrate the hidden fault feature. TQWT is introduced as it provides a vast wavelet dictionary with time-frequency localization ability. The parametric optimization is guided according to the maximization of fault feature ratio, which is a new quantitative measure of periodic fault signatures. The fault feature ratio is derived from the digital Hilbert demodulation analysis with an insightful quantitative interpretation. The output of ESW on the measured signal is a selected wavelet scale with indicated fault features. It is verified via numerical simulations that ESW can match the oscillatory behavior of signals without artificially specified. The proposed method is applied to two engineering cases, signals of which were collected from wind turbine and steel temper mill, to verify its effectiveness. The processed results demonstrate that the proposed method is more effective in extracting weak fault features of induction motor bearings compared with Fourier transform, direct Hilbert envelope spectrum, different wavelet transforms and spectral kurtosis.

A reliable approach to distinguish between transient with and without HFOs using TQWT and MCA.

Recent studies have reported that discrete high frequency oscillations (HFOs) in the range of 80-500Hz may serve as promising biomarkers of the seizure focus in humans. Visual scoring of HFOs is tiring, time consuming, highly subjective and requires a great deal of mental concentration. Due to the recent explosion of HFOs research, development of a robust automated detector is expected to play a vital role in studying HFOs and their relationship to epileptogenesis. Therefore, a handful of automated detectors have been introduced in the literature over the past few years. In fact, all the proposed methods have been associated with high false-positive rates, which essentially arising from filtered sharp transients like spikes, sharp waves and artifacts. In order to specifically minimize false positive rates and improve the specificity of HFOs detection, we proposed a new approach, which is a combination of tunable Q-factor wavelet transform (TQWT), morphological component analysis (MCA) and complex Morlet wavelet (CMW). The main findings of this study can be summarized as follows: The proposed method results in a sensitivity of 96.77%, a specificity of 85.00% and a false discovery rate (FDR) of 07.41%. Compared to this, the classical CMW method applied directly on the signals without pre-processing by TQWT-MCA achieves a sensitivity of 98.71%, a specificity of 18.75%, and an FDR of 29.95%. The proposed method may be considered highly accurate to distinguish between transients with and without HFOs. Consequently, it is remarkably reliable and robust for the detection of HFOs.

Feature extraction of rolling bearing’s early weak fault based on EEMD and tunable Q-factor wavelet transform

When early weak fault emerges in rolling bearing the fault feature is too weak to extract using the traditional fault diagnosis methods such as Fast Fourier Transform (FFT) and envelope demodulation. The tunable Q-factor wavelet transform (TQWT) is the improvement of traditional one single Q-factor wavelet transform, and it is very fit for separating the low Q-factor transient impact component from the high Q-factor sustained oscillation components when fault emerges in rolling bearing. However, it is hard to extract the rolling bearing’ early weak fault feature perfectly using the TQWT directly. Ensemble empirical mode decomposition (EEMD) is the improvement of empirical mode decomposition (EMD) which not only has the virtue of self-adaptability of EMD but also overcomes the mode mixing problem of EMD. The original signal of rolling bearing’ early weak fault is decomposed by EEMD and several intrinsic mode functions (IMFs) are obtained. Then the IMF with biggest kurtosis index value is selected and handled by the TQWT subsequently. At last, the envelope demodulation method is applied on the low Q-factor transient impact component and satisfactory extraction result is obtained.

Application of Wavelet Transform with Tunable Q-Factor to Analysis of Non-Stationary Harmonics

Harmonics of power system include steady and transient components, extraction and analysis of them can improve the power quality. Tunable Q-factor wavelet transform (TQWT), for which the Q-factor can be easily specified, is adopted to accomplish the extraction of non-stationary harmonic component from the noisy signal. The proposed method decomposes a signal into noise component and non-stationary harmonic component based on suitable Q-factor. Feasibility and effectiveness of the proposed method are verified by the simulation study.

Tunable Q-factor wavelet transform denoising with neighboring coefficients and its application to rotating machinery fault diagnosis

Fault diagnosis of rotating machinery is of great importance to the high quality products and long-term safe operation. However, the useful weak features are usually corrupted by strong background noise, thus increasing the difficulty of the feature extraction. Thereby, a novel denoising method based on the tunable Q-factor wavelet transform (TQWT) using neighboring coefficients is proposed in this article. The emerging TQWT possesses excellent properties compared with the conventional constant-Q wavelet transforms, which can tune Q-factor according to the oscillatory behavior of the signal. Meanwhile, neighboring coefficients denoising is adopted to avoid the overkill of conventional term-by-term thresholding techniques. Because of having the combined advantages of the two methods, the presented denoising method is more practical and effective than other methods. The proposed method is applied to a simulated signal, a rolling element bearing with an outer race defect from antenna transmission chain and a gearbox fault detection case. The processing results demonstrate that the proposed method can successfully identify the fault features, showing that this method is more effective than the conventional wavelet thresholding denoising methods, term-by-term TQWT denoising schemes and spectral kurtosis.